Skip to main content
Glama
hermoso-ai

Hermoso

Official

Post a video or photo post to TikTok

post_to_tiktok

Publish videos or photo slideshows to TikTok as a live post or draft, with captions, cover selection, and privacy controls.

Instructions

Publish to the user’s connected TikTok account — a finished VIDEO, or a PHOTO POST (TikTok’s photo/slideshow format). A photo post carries 1 to 35 images and ONE image is simply a one-slide photo post, so there is nothing special to do for a single picture: pass imageUrls, in the order the slides should appear, and optionally coverIndex. Pass videoUrl for a video. Never pass both — TikTok has no mixed post. TWO destinations either way: destination:"post" puts it LIVE on their profile now — that requires privacy, and you must call tiktok_creator_info first, show the creator’s real privacy options and get an explicit yes before calling. destination:"draft" (the default, and the safer one) sends it to TikTok for the user to finish and post themselves from the app. Pass Hermoso render URLs (or upload_file urls for local/external files). Needs TikTok connected (Settings ▸ Connectors ▸ TikTok).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
hookNoWHAT ANGLE THIS POST IS BUILT ON — the single most valuable field here, and the only moment it can ever be recorded. post_performance groups on it to answer "which hooks work", and it needs 5 posts sharing ONE hook before it will call anything a winner, so REUSE THE SAME WORDING across a campaign instead of rephrasing it every time. Best of all, pass a hook id from list_hooks (e.g. "direct_callout", "mid_problem", "before_after") — those fold onto a stable key however they are spelled, so a whole brand accumulates evidence on one row. Your own wording is fine too; it just only groups when you repeat it exactly. Omitting it means this post can never vote on which hook works.
titleNothe caption — hashtags go here (video ≤2200 chars, photo post ≤4000)
privacyNoREQUIRED for destination:"post", for photos and video alike. Must be one the creator actually allows — read them from tiktok_creator_info, never guess.
subjectNoWHAT THIS POST IS ABOUT — the product, feature, offer or theme (e.g. "winter coat", "free trial", "founder story"). The second grouping axis in post_performance. Same rule as hook: reuse the exact wording so posts about one subject land in one group.
videoUrlNothe video to post — a Hermoso render URL or an upload_file url. Omit for a photo post.
imageUrlsNoa PHOTO POST: 1–35 image URLs in slide order. One url = a single-image photo post. Do not combine with videoUrl.
yourBrandNodiscloses that this promotes the creator’s own brand
coverIndexNophoto posts: which slide is the cover, 0-based. Default 0 (the first slide).
photoTitleNophoto posts only: a short title above the caption (≤90 chars). Defaults to the caption’s first line.
destinationNo"post" = live on the profile now (needs privacy + an explicit user yes); "draft" = to TikTok for the user to review and post themselves. Default "draft".
disableDuetNovideo only — TikTok has no duet on a photo post
autoAddMusicNophoto posts only: let TikTok add a recommended track (default true — a silent slideshow reads as broken)
disableStitchNovideo only — TikTok has no stitch on a photo post
brandedContentNodiscloses a paid partnership — cannot be combined with SELF_ONLY privacy
disableCommentNo
coverTimestampMsNovideo only: which frame to use as the cover, in ms
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate readOnlyHint=false and idempotentHint=false, but the description goes far beyond that by disclosing that 'post' makes the content live immediately and requires explicit user approval, while 'draft' is safer. It also explains platform constraints like the lack of mixed video/photo posts, the default autoAddMusic=true to avoid silent slideshows, and the connector prerequisite. No contradictions with annotations; the description adds substantial behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, dense paragraph but well-structured: it starts with the core purpose, then details video vs. photo, then destinations, then prerequisites and strategic tips. Every sentence adds value for a tool with 16 parameters and conditional logic, though it could be slightly more scannable with bullet points. It is not overly verbose and front-loads the most critical distinction (post vs. draft).

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (16 parameters, multiple modes, and platform-specific rules), the description covers the essential points: the two content types, the two destinations with their implications, the consent requirement, the connector prerequisite, the analytics grouping hints, and platform constraints (no mixed posts, photo-title default, autoAddMusic behavior). No output schema exists, but that's acceptable; the description is complete enough for an agent to call this tool correctly and safely.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 94%, so the schema already documents parameters well. The description adds strategic meaning beyond the schema, particularly for 'hook' and 'subject', explaining they serve as grouping keys for post_performance analytics and the importance of reusing exact wording. It also clarifies the constraint that videoUrl and imageUrls are mutually exclusive, and explains defaults like coverIndex=0 and photoTitle fallback. This enriches the schema without redundancy.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states the verb ('Publish to the user’s connected TikTok account') and resource, distinguishes video vs. photo post formats, and clarifies that a single image is just a one-slide photo post. This clearly separates it from other post_to_* tools (e.g., post_to_meta, post_to_x) and from TikTok-specific utilities like tiktok_creator_info or list_tiktok_videos.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit usage context: when to use 'post' vs 'draft' (and the safety rationale), the prerequisite of a connected TikTok account, the requirement to call tiktok_creator_info first for privacy options and get explicit consent for live posting, and the prohibition on passing both videoUrl and imageUrls. It also notes the default destination and mentions when to use coverIndex. This is comprehensive and leaves little to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/hermoso-ai/hermoso'

If you have feedback or need assistance with the MCP directory API, please join our Discord server